sketchkit.colorization.models package

Submodules

sketchkit.colorization.models.controlnet_lineart module

ControlNet Lineart Model for Sketch Colorization

class sketchkit.colorization.models.controlnet_lineart.ControlNetLineartModel(device: str = 'cuda', controlnet_model: str = 'lllyasviel/control_v11p_sd15_lineart', sd_model: str = 'runwayml/stable-diffusion-v1-5', torch_dtype: dtype = torch.float16, safety_checker: bool = False, **kwargs: Any)

Bases: object

ControlNet model with lineart conditioning for sketch colorization.

generate(control_image: Image, prompt: str, size: int | Tuple[int, int] = 512, negative_prompt: str = 'blurry, low quality, distorted', num_inference_steps: int = 20, guidance_scale: float = 7.5, controlnet_conditioning_scale: float = 1.0, seed: int | None = None, **kwargs: Any) → Image

Generate colorized image from lineart sketch.

sketchkit.colorization.models.controlnet_scribble module

ControlNet Scribble Model for Sketch Colorization

class sketchkit.colorization.models.controlnet_scribble.ControlNetScribbleModel(device: str = 'cuda', controlnet_model: str = 'lllyasviel/sd-controlnet-scribble', sd_model: str = 'runwayml/stable-diffusion-v1-5', torch_dtype: dtype = torch.float16, safety_checker: bool = False, **kwargs: Any)

Bases: object

ControlNet model with scribble conditioning for sketch colorization.

generate(control_image: Image, prompt: str, size: int | Tuple[int, int] = 512, negative_prompt: str = 'blurry, low quality, distorted', num_inference_steps: int = 20, guidance_scale: float = 7.5, controlnet_conditioning_scale: float = 1.0, seed: int | None = None, **kwargs: Any) → Image

Generate colorized image from scribble sketch.

Module contents

Colorization Models Module

This module contains all AI model implementations for sketch colorization.

class sketchkit.colorization.models.ControlNetLineartModel(device: str = 'cuda', controlnet_model: str = 'lllyasviel/control_v11p_sd15_lineart', sd_model: str = 'runwayml/stable-diffusion-v1-5', torch_dtype: dtype = torch.float16, safety_checker: bool = False, **kwargs: Any)

Bases: object

ControlNet model with lineart conditioning for sketch colorization.

generate(control_image: Image, prompt: str, size: int | Tuple[int, int] = 512, negative_prompt: str = 'blurry, low quality, distorted', num_inference_steps: int = 20, guidance_scale: float = 7.5, controlnet_conditioning_scale: float = 1.0, seed: int | None = None, **kwargs: Any) → Image

Generate colorized image from lineart sketch.

class sketchkit.colorization.models.ControlNetScribbleModel(device: str = 'cuda', controlnet_model: str = 'lllyasviel/sd-controlnet-scribble', sd_model: str = 'runwayml/stable-diffusion-v1-5', torch_dtype: dtype = torch.float16, safety_checker: bool = False, **kwargs: Any)

Bases: object

ControlNet model with scribble conditioning for sketch colorization.

generate(control_image: Image, prompt: str, size: int | Tuple[int, int] = 512, negative_prompt: str = 'blurry, low quality, distorted', num_inference_steps: int = 20, guidance_scale: float = 7.5, controlnet_conditioning_scale: float = 1.0, seed: int | None = None, **kwargs: Any) → Image

Generate colorized image from scribble sketch.